基于色彩衰减补偿和Retinex的水下图像增强

针对水下图像存在的色偏、雾状模糊、低曝光和非均匀光照问题, 提出一种基于色彩衰减补偿和Retinex的水下图像增强算法. 首先, 为校正水下图像的色偏, 利用水体对不同波长光线衰减不一致的特性自适应地补偿其R、G、B通道. 然后, 使用基于多尺度导向滤波的Retinex去除雾状模糊, 增强对比度. 最后, 根据水下图像和自然图像的直方图分布特征对其进行归一化处理, 从而在保存图像主要信息的前提下增强其纹理和曝光. 实验结果表明, 该算法不但具有较优的视觉感知效果, 而且具有较高的图像质量评价分数. 该算法具有较强的适应性, 有助于计算机视觉算法在水下的应用.

Underwater image enhancement based on color attenuation compensation and Retinex

To tackle the problems of color cast, foggy blur, low exposure and non-uniform illumination in underwater images, an underwater image enhancement algorithm is proposed based on attenuation compensation of color and the theory of Retinex. Firstly, in order to correct the color cast in underwater images, the red, green, and blue channel are adaptively compensated, which is achieved by using the different wavelengths of light attenuated accordingly. Then, the Retinex based on multi-scale guided filtering is used to remove foggy blur and improve contrast. Finally, the deblurred underwater image is normalized according to histogram distribution of the underwater image and the natural image, which enhances its texture and exposure on the premise of retaining the main information of images. The experimental results show that the proposed algorithm not only offers the best visual perception, but also achieves the highest score of image quality evaluation. The proposed algorithm features high adaptability, and may provide references for research in underwater target identification.